Use diff ids from image configuration

The diff id resolution currently relies on a stored mapping for
archive digest to diff id. This mapping could be derived from
the image configuration if the image configuration is available.
On linux the image config is pulled in parallel and may not be
available. On windows, however, it is always pulled first and can
be used to supplement the stored mapping for images which may not
have this mapping from being side loaded. This becomes useful when
combined with side loaded foreign layers.

Signed-off-by: Derek McGowan <derek@mcgstyle.net>
Upstream-commit: 633f9252b8e066ef7a1a738ddc84c3970379844e
Component: engine

components/engine/distribution/pull_v2.go

@@ -131,6 +131,7 @@ func (p *v2Puller) pullV2Repository(ctx context.Context, ref reference.Named) (e
 
 type v2LayerDescriptor struct {
 	digest            digest.Digest
+	diffID            layer.DiffID
 	repoInfo          *registry.RepositoryInfo
 	repo              distribution.Repository
 	V2MetadataService metadata.V2MetadataService
@@ -148,6 +149,9 @@ func (ld *v2LayerDescriptor) ID() string {
 }
 
 func (ld *v2LayerDescriptor) DiffID() (layer.DiffID, error) {
+	if ld.diffID != "" {
+		return ld.diffID, nil
+	}
 	return ld.V2MetadataService.GetDiffID(ld.digest)
 }
 
@@ -575,6 +579,16 @@ func (p *v2Puller) pullSchema2(ctx context.Context, ref reference.Named, mfst *s
 		if configRootFS == nil {
 			return "", "", errRootFSInvalid
 		}
+
+		if len(descriptors) != len(configRootFS.DiffIDs) {
+			return "", "", errRootFSMismatch
+		}
+
+		// Populate diff ids in descriptors to avoid downloading foreign layers
+		// which have been side loaded
+		for i := range descriptors {
+			descriptors[i].(*v2LayerDescriptor).diffID = configRootFS.DiffIDs[i]
+		}
 	}
 
 	if p.config.DownloadManager != nil {